Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3248 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4683. Min Act: -0.0000

Data Index: 190910 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4701. Min Act: -0.0000

Data Index: 836598 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.5093. Min Act: -0.0000

Data Index: 34391 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4497. Min Act: -0.0000

Data Index: 732411 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4498. Min Act: -0.0000

Data Index: 379997 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1308721 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4277. Min Act: -0.0000

Data Index: 767387 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4076. Min Act: -0.0000

Data Index: 496512 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4547. Min Act: -0.0000

Data Index: 867693 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4084. Min Act: -0.0000

Data Index: 807353 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.3932. Min Act: -0.0000

Data Index: 816978 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4187. Min Act: -0.0000

Data Index: 991755 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.4049. Min Act: -0.0000

Data Index: 367599 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1233220 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1144836 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.3877. Min Act: -0.0000

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.3943. Min Act: -0.0000

Data Index: 560150 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.5093. Min Range: -0.5093

Max Act: 0.3859. Min Act: -0.0000

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 680